Problem
Research questions and friction points this paper is trying to address.
remote awareness
seafloor images
AUV
low-bandwidth communication
real-time transmission
Remote Awareness of Seafloor Images Collected by AUVs over Low-Bandwidth Communication Links
🤖 AI Summary
This study addresses the challenge of real-time data transmission in autonomous underwater vehicle (AUV) missions, where massive volumes of seafloor imagery cannot be relayed promptly to shore-based operators under severe bandwidth constraints of underwater acoustic or satellite links. To enable timely situational awareness, the authors propose an AI-driven image summarization method that intelligently selects a representative subset of images—or those most relevant to a given query—fuses them with associated metadata, and transmits the compact summary via low-bandwidth channels. Field trials in real marine environments demonstrate that during a 2-hour 47-minute survey mission, the system transmitted a meaningful visual summary in just 34 minutes, achieving an effective data compression ratio of nearly 400,000:1 while preserving critical mission context for remote operators.
📝 Abstract
This paper introduces a method for real-time processing and transmission of autonomous underwater vehicle (AUV) imagery over low-bandwidth communication links. It leverages artificial intelligence (AI) techniques to identify a set of images that best represent an entire dataset, or automatically finds the most similar images to a given query image for transmission to operators. Combined with metadata of a larger set of images, compressed versions of the selected images can be transmitted over satellite communication links or underwater modems, and provide operators on shore with information about the type of imagery the AUV is collecting while it is still deployed. Data from three deployments off the coast of the UK and in Gran Canaria using different AUVs and imaging systems demonstrate the method in the field. It achieved an almost 400,000-fold reduction in data volume compared to the raw data size, enabling transmission of data summaries of a 2-hour 47-minute-long mapping mission in just over 34 minutes over low-bandwidth satellite communication.
Innovation
Methods, ideas, or system contributions that make the work stand out.
AI-based image selection
low-bandwidth communication
autonomous underwater vehicle (AUV)
image summarization
real-time data transmission
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
